Treffer: An explanation of the effectiveness of latent semantic indexing by means of a Bayesian regression model
Title:
An explanation of the effectiveness of latent semantic indexing by means of a Bayesian regression model
Authors:
Source:
Information processing & management. 32(3):329-344
Publisher Information:
Oxford: Elsevier Science, 1996.
Publication Year:
1996
Physical Description:
print, 15 ref
Original Material:
INIST-CNRS
Subject Terms:
Information and communication sciences, Sciences de l'information communication, Documentation, Computer science, Informatique, Sciences exactes et technologie, Exact sciences and technology, Sciences et techniques communes, Sciences and techniques of general use, Sciences de l'information. Documentation, Information science. Documentation, Traitement et recherche de l'information, Information processing and retrieval, Structure et analyse des documents et de l'information, Information and document structure and analysis, Analyse des contenus, Content analysis, Indexation. Classification. Résumé. Synthèses, Indexing. Classification. Abstracting. Syntheses, Sciences de l'information et de la communication, Information and communication sciences, Traitement et recherche d'information, Informatique documentaire, Documentation data processing, Información documental, Analyse automatique, Automatic analysis, Análisis automático, Estimation Bayes, Bayes estimation, Estimación Bayes, Modèle régression, Regression model, Modelo regresión, Modèle variable latente, Latent variable model, Modelo variable latente, Pertinence, Relevance, Pertinencia, Représentation par terme indexation, Search pattern, Representación por término indexación, Régression multiple, Multiple regression, Regresión múltiple, Régression statistique, Statistical regression, Regresión estadística, Système documentaire, Document retrieval system, Sistema recuperación documental, Système recherche, Search system, Sistema investigación, Explication, Explanation, Indexation sémantique latente, Latent semantic indexing, Latent semantic indexing (LSI), Mathématisation, Mathematization
Document Type:
Fachzeitschrift
Article
File Description:
text
Language:
English
Author Affiliations:
Bell Communications Research (Bellcore), 331 Newman Springs Road, Red Bank, NJ 07701-5699, United States
ISSN:
0306-4573
Rights:
Copyright 1996 INIST-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
CC BY 4.0
Sauf mention contraire ci-dessus, le contenu de cette notice bibliographique peut être utilisé dans le cadre d’une licence CC BY 4.0 Inist-CNRS / Unless otherwise stated above, the content of this bibliographic record may be used under a CC BY 4.0 licence by Inist-CNRS / A menos que se haya señalado antes, el contenido de este registro bibliográfico puede ser utilizado al amparo de una licencia CC BY 4.0 Inist-CNRS
Notes:
Sciences of information and communication. Documentation
FRANCIS
FRANCIS
Accession Number:
edscal.3103072
Database:
PASCAL Archive
Weitere Informationen
Latent Semantic Indexing (LSI) is an effective automated method for determining if a document is relevant to a reader based on a few words or an abstract describing the reader's needs. A particular feature of LSI is its ability to deal automatically with synonyms. LSI generally is explained in terms of a mathematical concept called the Singular Value Decomposition and statistical methods such as factor analysis. This paper looks at LSI from a different perspective, comparing it to statistical regression and Bayesian methods. The relationships found can be useful in explaining the performance of LSI and in suggesting variations on the LSI approach.